prior_art_search

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full load. It does disclose meaningful behavior beyond the schema: the text is compared against the ledger and never stored, and the two lookup modes are semantic versus exact-match. It does not state whether this is strictly read-only, whether any submission path is implied, or what the response contains (match records, timestamps, recorder identity).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core check and the timing rule, then the parameter guidance. The prose is efficient, with only mild rhetorical flourishes ("record yours now and anyone can check its date") that still convey the value proposition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and zero parameter descriptions, the definition needs to do more of the work itself. It covers the why and the two input modes well, but an agent is left guessing at result shape, what a match record looks like, and whether `limit` bounds ranked semantic hits or exact matches.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and all three parameters are bare strings/integer with defaults, so the description must compensate. It does explain `text` (semantic search) and `output_hash` (exact match, for content you would rather not send) and the either/or relationship between them, but `limit` is never mentioned and the default of 5 is left undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: check whether something like this already exists on the public ledger and who recorded it first. It distinguishes itself from the registration siblings only implicitly ("BEFORE publishing or registering", "record yours now") rather than by naming notarize_hash or claim_authorship, so it is clear but does not fully close the loop on sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit timing guidance: run this before publishing or registering, and it explains both branches of the outcome (prior art found → change course; none found → record now). What is missing is an explicit pointer to the specific alternative tool to use in the second branch.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.